Hacker News new | ask | show | jobs
by arisAlexis 266 days ago
They have 10x inference speed. Try Mistral and get awed.
1 comments
aurareturn 266 days ago
They're roughly 2.5x faster. https://www.cerebras.ai/press-release/maverick

Not 10x. But at greater cost and lower scale.

link
arisAlexis 266 days ago
Sources for greater cost and lower scale?
link